detecting-malicious-scheduled-tasks-with-sysmon

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Windows Event Log data via scripts/agent.py, which extracts command lines and task content. This content is then presented to the agent, creating a surface where malicious instructions embedded in the logs could potentially influence the agent's behavior.
  • Ingestion points: scripts/agent.py:parse_evtx_xml reads XML files from the filesystem provided via command-line arguments.
  • Boundary markers: Extracted log content is displayed without specific delimiters or instructions for the agent to ignore embedded commands.
  • Capability inventory: The skill is restricted to local file reading and console output; it does not contain built-in subprocess execution, shell commands, or network access.
  • Sanitization: Extracted content is truncated for display length but not specifically sanitized or escaped for prompt safety, relying on the agent's internal guardrails for processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 11:04 PM